Cardiotocography (CTG) is a monitoring technique used routinely during the pregnancy and labor and including the analysis of fetal heart rates and movements with uterine contractions. The fact that CTG signals are interpreted by experts generally with eye and CTG has high false positive rate results in intra- and inter-observer conflicts and causes the observers to frequently notice real pathological cases. Therefore, various computer-aided methods supporting diagnosis process have been developed. In this study, a new approach is suggested based on signal and image processing techniques in order to provide the classification of CTG signals. In particular, morphological, spectral and statistical properties of CTG signals are obtained with the way defined conventionally. A spectrum of the signals containing time-frequency information was transformed into 8-bit gray-level image and it was enabled to build gray level co-occurrence matrix (GLCM). In the final step, a combination of morphological, statistical, spectral and image-based properties was applied as the input to the artificial neural network (ANN). In order to measure the performance of the proposed method, accuracy, sensitivity, specificity and quality indexes were used. The obtained results revealed that image-based features increased the classification success and they gave the best results when they were used with the conventional features.